Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 890 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1918. Min Act: -0.0001

Data Index: 324498 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1795. Min Act: -0.0001

Data Index: 1258586 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1892. Min Act: -0.0001

Data Index: 1225274 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1797. Min Act: -0.0001

Data Index: 137499 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1840. Min Act: -0.0001

Data Index: 648644 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1780. Min Act: -0.0001

Data Index: 671904 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1766. Min Act: -0.0001

Data Index: 989313 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1627. Min Act: -0.0001

Data Index: 841644 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1465. Min Act: -0.0001

Data Index: 1265759 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1577. Min Act: -0.0001

Data Index: 1278476 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1505. Min Act: -0.0001

Data Index: 452362 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1558. Min Act: -0.0001

Data Index: 1361358 (Python Code)

Max Activating Token Index: 100

Text #12

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1543. Min Act: -0.0001

Data Index: 374881 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1529. Min Act: -0.0001

Data Index: 533002 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1517. Min Act: -0.0001

Data Index: 1518306 (Python Code)

Max Activating Token Index: 84

Text #15

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1491. Min Act: -0.0001

Data Index: 1243159 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1485. Min Act: -0.0001

Data Index: 1276301 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1441. Min Act: -0.0001

Data Index: 1559209 (Python Code)

Max Activating Token Index: 191

Text #18

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1475. Min Act: -0.0001

Data Index: 1413836 (Python Code)

Max Activating Token Index: 71

Text #19

Max Range: 0.1918. Min Range: -0.1918

Max Act: 0.1392. Min Act: -0.0001

Data Index: 1526672 (Python Code)

Max Activating Token Index: 271